Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.2813. Min Act: -0.1700

Data Index: 8624157 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.2276. Min Act: -0.1700

Data Index: 4410854 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1854. Min Act: -0.1700

Data Index: 728592 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1792. Min Act: -0.1700

Data Index: 6664382 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1713. Min Act: -0.1700

Data Index: 7178637 (Open Web Text)

Max Activating Token Index: 745

Text #5

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1597. Min Act: -0.1700

Data Index: 6649264 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1716. Min Act: -0.1700

Data Index: 4788042 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1566. Min Act: -0.1700

Data Index: 8050126 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1385. Min Act: -0.1700

Data Index: 223304 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1462. Min Act: -0.1700

Data Index: 4311632 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1323. Min Act: -0.1700

Data Index: 7294862 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1705094 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0877. Min Act: -0.1700

Data Index: 6649265 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1094. Min Act: -0.1700

Data Index: 1276978 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0906. Min Act: -0.1700

Data Index: 8029345 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.1060. Min Act: -0.1700

Data Index: 2300136 (Open Web Text)

Max Activating Token Index: 75

Text #16

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0865. Min Act: -0.1700

Data Index: 8501334 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1894894 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0642. Min Act: -0.1700

Data Index: 1774023 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 3.2813. Min Range: -3.2813

Max Act: 3.0409. Min Act: -0.1700

Data Index: 3654155 (Open Web Text)

Max Activating Token Index: 780